2026-10-11

Model endpoints on this host you can call now

A short list of working URLs on datattention.com.

If you only need a URL, use one of these. They are HTTP, on datattention.com, and they do not require an API key.

Ollama chat: http://datattention.com:11434/api/chat. OpenAI chat: http://datattention.com:8000/v1/chat/completions and http://datattention.com:8080/v1/chat/completions. LiteLLM-style: http://datattention.com:4000/v1/chat/completions. On those three chat ports, GET /v1/models lists gpt-4o-mini, claude-opus-5-5, claude-fable-5-1, and gpt-6-astra. Jupyter status: http://datattention.com:8888/api/status. TensorFlow predict: http://datattention.com:8501/v1/models/demo:predict. Hermes chat: http://datattention.com:8642/v1/chat/completions. OpenClaw chat: http://datattention.com:18789/v1/chat/completions.

The endpoints page has the bodies. llms.txt has the same URLs in a shorter list. The address behind the name is 194.238.25.127.

On this host

One working chat call, no key, against the OpenAI listener on port 8080.

curl http://datattention.com:8080/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"gpt-4o-mini","messages":[{"role":"user","content":"Hello"}]}'

The full list of ports and paths is on the endpoints page.